Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

A system hierarchy for brain-inspired computing

Nature volume 586, pages 378–384 (2020)Cite this article

Subjects

Abstract

Neuromorphic computing draws inspiration from the brain to provide computing technology and architecture with the potential to drive the next wave of computer engineering1,2,3,4,5,6,7,8,9,10,11,12,13. Such brain-inspired computing also provides a promising platform for the development of artificial general intelligence14,15. However, unlike conventional computing systems, which have a well established computer hierarchy built around the concept of Turing completeness and the von Neumann architecture16,17,18, there is currently no generalized system hierarchy or understanding of completeness for brain-inspired computing. This affects the compatibility between software and hardware, impairing the programming flexibility and development productivity of brain-inspired computing. Here we propose ‘neuromorphic completeness’, which relaxes the requirement for hardware completeness, and a corresponding system hierarchy, which consists of a Turing-complete software-abstraction model and a versatile abstract neuromorphic architecture. Using this hierarchy, various programs can be described as uniform representations and transformed into the equivalent executable on any neuromorphic complete hardware—that is, it ensures programming-language portability, hardware completeness and compilation feasibility. We implement toolchain software to support the execution of different types of program on various typical hardware platforms, demonstrating the advantage of our system hierarchy, including a new system-design dimension introduced by the neuromorphic completeness. We expect that our study will enable efficient and compatible progress in all aspects of brain-inspired computing systems, facilitating the development of various applications, including artificial general intelligence.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Hierarchies of the brain-inspired computing system and traditional computing systems.
Fig. 2: POG, EPG and ANA.
Fig. 3: Toolchain and bicycle driving and tracking experiment.
Fig. 4: Experimental results.

Similar content being viewed by others

Data availability

The example applications that we used are publicly available, as described in the text and the relevant references. The experimental setups for demonstration and measurements are detailed in the text and the relevant references. Other data that support the findings of this study are available from the corresponding authors on reasonable request.

Code availability

The codes used for the software toolchain and the demonstration neural networks are available from the corresponding authors on reasonable request.

References

  1. Waldrop, M. The chips are down for Moore’s law. Nature 530, 144–147 (2016).

    Article  CAS  ADS  PubMed  Google Scholar 

  2. Kendall, J. D. & Kumar, S. The building blocks of a brain-inspired computer. Appl. Phys. Rev. 7, 011305 (2020).

    Article  CAS  ADS  Google Scholar 

  3. Zhang, B., Shi, L. P. & Song, S. Creating more intelligent robots through brain-inspired computing. Science 354 (Spons. Suppl.), 4–9 (2016).

    Google Scholar 

  4. Roy, K., Jaiswal, A. & Panda, P. Towards spike-based machine intelligence with neuromorphic computing. Nature 575, 607–617 (2019).

    Article  CAS  ADS  PubMed  Google Scholar 

  5. Chen, Y. et al. DianNao family: energy-efficient hardware accelerators for machine learning. Commun. ACM 59, 105–112 (2016).

    Article  ADS  Google Scholar 

  6. Jouppi, N. P. et al. In-datacenter performance analysis of a tensor processing unit. In Proc. 44th Annu. Int. Symp. Computer Architecture 1–12 (IEEE, 2017).

  7. Schemmel, J. et al. A wafer-scale neuromorphic hardware system for large-scale neural modeling. In Proc. 2010 IEEE Int. Symp. Circuits and Systems 1947–1950 (IEEE, 2010).

  8. Merolla, P. A. et al. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345, 668–673 (2014).

    Article  CAS  ADS  PubMed  Google Scholar 

  9. Furber, S. B. et al. The spinnaker project. Proc. IEEE 102, 652–665 (2014).

    Article  Google Scholar 

  10. Davies, M. et al. Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro 38, 82–99 (2018).

    Article  Google Scholar 

  11. Benjamin, B. V. et al. Neurogrid: a mixed-analog-digital multichip system for large-scale neural simulations. Proc. IEEE 102, 699–716 (2014).

    Article  Google Scholar 

  12. Friedmann, S. et al. Demonstrating hybrid learning in a flexible neuromorphic hardware system. IEEE Trans. Biomed. Circuits Syst. 11, 128–142 (2017).

    Article  PubMed  Google Scholar 

  13. Neckar, A. et al. Braindrop: a mixed-signal neuromorphic architecture with a dynamical systems-based programming model. Proc. IEEE 107, 144–164 (2019).

    Article  Google Scholar 

  14. Pei, J. et al. Towards artificial general intelligence with hybrid Tianjic chip architecture. Nature 572, 106–111 (2019).

    Article  CAS  ADS  PubMed  Google Scholar 

  15. Goertzel, B. Artificial general intelligence: concept, state of the art, and future prospects. J. Artif. Gen. Intell. 5, 1–48 (2014).

    Article  Google Scholar 

  16. Turing, A. M. On computable numbers, with an application to the Entscheidungsproblem. Proc. Lond. Math. Soc. 2, 230–265 (1937).

    Article  MathSciNet  Google Scholar 

  17. Eckert, J. P. Jr & Mauchly, J. W. Automatic High-speed Computing: A Progress Report on the EDVAC. Report No. W-670-ORD-4926 (Univ. Pennsylvania, 1945).

  18. von Neumann, J. First draft of a report on the EDVAC. IEEE Ann. Hist. Comput. 15, 27–75 (1993).

    Article  MathSciNet  Google Scholar 

  19. Aimone, J. B., Severa, W. & Vineyard, C. M. Composing neural algorithms with Fugu. In Proc. Int. Conf. Neuromorphic Systems 1–8 (ACM, 2019).

  20. Lagorce, X. & Benosman, R. Stick: spike time interval computational kernel, a framework for general purpose computation using neurons, precise timing, delays, and synchrony. Neural Comput. 27, 2261–2317 (2015).

    Article  MathSciNet  PubMed  Google Scholar 

  21. Aimone, J. B. et al. Non-neural network applications for spiking neuromorphic hardware. Proc. 3rd Int. Worksh. Post Moores Era Supercomputing 24–26 (IEEE–TCHPC, 2018).

  22. Sawada, J. et al. Truenorth ecosystem for brain-inspired computing: scalable systems, software, and applications. In Proc. Int. Conf. High Performance Computing, Networking, Storage and Analysis 130–141 (IEEE, 2016).

  23. Rowley, A. G. D. et al. SpiNNTools: the execution engine for the SpiNNaker platform. Front. Neurosci. 13, 231 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  24. Rhodes, O. et al. sPyNNaker: a software package for running PyNN simulations on SpiNNaker. Front. Neurosci. 12, 816 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  25. Lin, C. K. et al. Programming spiking neural networks on Intel’s Loihi. Computer 51, 52–61 (2018).

    Article  Google Scholar 

  26. Davison, A. P. et al. PyNN: a common interface for neuronal network simulators. Front. Neuroinform. 2, 11 (2009).

    ADS  PubMed  PubMed Central  Google Scholar 

  27. Bekolay, T. et al. Nengo: a Python tool for building large-scale functional brain models. Front. Neuroinform. 7, 48 (2014).

    Article  PubMed  PubMed Central  Google Scholar 

  28. Hashmi, A., Nere, A., Thomas, J. J. and Lipasti, M. A case for neuromorphic ISAs. In ACM SIGARCH Computer Architecture News Vol. 39, 145–158 (ACM, 2011).

  29. Schuman, C. D. et al. A survey of neuromorphic computing and neural networks in hardware. Preprint at https://arxiv.org/abs/1705.06963 (2017).

  30. LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).

    Article  CAS  ADS  Google Scholar 

  31. Poggio, T. & Girosi, F. Networks for approximation and learning. Proc. IEEE 78, 1481–1497 (1990).

    Article  Google Scholar 

  32. Esmaeilzadeh, H., Sampson, A., Ceze, L. & Burger, D. Neural acceleration for general-purpose approximate programs. IEEE Micro 33, 16–27 (2013).

    Article  Google Scholar 

  33. Mead, C. & Ismail, M. Analog VLSI Implementation of Neural Systems Ch. 5–6 (Springer, 1989).

  34. Strukov, D. B., Snider, G. S., Stewart, D. R. & Williams, R. S. The missing memristor found. Nature 453, 80–83 (2008).

    Article  CAS  ADS  PubMed  Google Scholar 

  35. Prezioso, M. et al. Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature 521, 61–64 (2015).

    Article  CAS  ADS  PubMed  Google Scholar 

  36. Ji, Y. et al. FPSA: a full system stack solution for reconfigurable ReRAM-based NN accelerator architecture. In Proc. 24th Int. Conf. Architectural Support for Programming Languages and Operating Systems 733–747 (ACM, 2019).

  37. Tuma, T., Pantazi, A., Le Gallo, M., Sebastian, A. & Eleftheriou, E. Stochastic phase-change neurons. Nat. Nanotechnol. 11, 693–699 (2016).

    Article  CAS  ADS  PubMed  Google Scholar 

  38. Negrov, D. et al. An approximate backpropagation learning rule for memristor based neural networks using synaptic plasticity. Neurocomputing 237, 193–199 (2016).

    Article  Google Scholar 

  39. Maass, W. Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10, 1659–1671 (1997).

    Article  Google Scholar 

  40. Leshno, M. et al. Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Netw. 6, 861–867 (1993).

    Article  Google Scholar 

  41. Dennis, J. B., Fosseen, J. B. & Linderman, J. P. Data flow schemas. In Int. Symp. Theoretical Programming 187–216 (Springer, 1974).

  42. Jagannathan, R. Coarse-grain dataflow programming of conventional parallel computers. In Advanced Topics in Dataflow Computing and Multithreading 113–129 (IEEE, 1995).

  43. Zhang, W. & Yang, Y. A survey of mathematical modeling based on flocking system. Vibroengineering PROCEDIA 13, 243–248 (2017).

    Article  Google Scholar 

  44. Hennessy, J. & Patterson, D. A new golden age for computer architecture. Commun. ACM 62, 48–60 (2019).

    Article  Google Scholar 

  45. Deng, L. et al. Tianjic: a unified and scalable chip bridging spike-based and continuous neural computation. IEEE J. Solid-State Circuits 55, 2228–2246 (2020).

    Article  ADS  Google Scholar 

  46. Dong, X. et al. Nvsim: a circuit-level performance, energy, and area model for emerging nonvolatile memory. IEEE Trans. Comput. Aided Des. Integrated Circ. Syst. 31, 994–1007 (2012).

    Article  Google Scholar 

  47. Cong, J. & Xiao, B. mrFPGA: a novel FPGA architecture with memristor-based reconfiguration. In 2011 IEEE/ACM Int. Symp. Nanoscale Architectures 1–8 (IEEE, 2011).

  48. Luu, J. et al. VTR 7.0: next generation architecture and CAD system for FPGAs. ACM Trans. Reconfig. Technol. Syst. 7, 6 (2014).

    Article  Google Scholar 

  49. Reynolds, C. W. Flocks, herds and schools: a distributed behavioral model. In Proc. 14th Annu. Conf. Computer Graphics and Interactive Techniques 25–34 (ACM, 1987).

  50. Bajec, I. L., Zimic, N. & Mraz, M. The computational beauty of flocking: boids revisited. Math. Comput. Model. Dyn. Syst. 13, 331–347 (2007).

    Article  MathSciNet  Google Scholar 

  51. Parker, C. XBoids, GPL version 2 licensed. http://www.vergenet.net/~conrad/boids/download (2002).

  52. Aslan, S., Niu, S. & Saniie, J. FPGA implementation of fast QR decomposition based on givens rotation. Proc. 55th Int. Midwest Symp. Circuits and Systems 470–473 (IEEE, 2012).

Download references

Acknowledgements

This work was partly supported by Beijing Academy of Artificial Intelligence (No. BAAI2019ZD0403), NSFC (No. 61836004), Brain-Science Special Program of Beijing under grant Z181100001518006, Beijing National Research Center for Information Science and Technology, Beijing Innovation Center for Future Chips, Tsinghua University and Tsinghua University-China Electronics Technology HIK Group Co. Joint Research Center for Brain-inspired Computing, JCBIC.

Author information

Author notes

  1. These authors contributed equally: Youhui Zhang, Peng Qu, Yu Ji, Weihao Zhang

Authors and Affiliations

  1. Department of Computer Science and Technology, Tsinghua University, Beijing, China

    Youhui Zhang, Peng Qu, Yu Ji, Wenguang Chen & Weimin Zheng

  2. Center for Brain-Inspired Computing Research (CBICR), Tsinghua University, Beijing, China

    Youhui Zhang, Peng Qu, Yu Ji, Weihao Zhang, Guanrui Wang, Sen Song, Guoqi Li, Feng Chen, Jing Pei, Rong Zhao, Mingguo Zhao & Luping Shi

  3. Beijing National Research Center for Information Science and Technology, Beijing, China

    Youhui Zhang, Peng Qu, Yu Ji, Wenguang Chen & Weimin Zheng

  4. Department of Precision Instruments, Tsinghua University, Beijing, China

    Weihao Zhang, Guanrui Wang, Guoqi Li, Jing Pei & Luping Shi

  5. Department of Electrical and Computer Engineering, University of Delaware, Newark, DE, USA

    Guangrong Gao

  6. Department of Biomedical Engineering, Tsinghua University, Beijing, China

    Sen Song

  7. Department of Automation, Tsinghua University, Beijing, China

    Feng Chen & Mingguo Zhao

Authors
  1. Youhui Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Peng Qu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yu Ji
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Weihao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Guangrong Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Guanrui Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Sen Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Guoqi Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Wenguang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Weimin Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Feng Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Jing Pei
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Rong Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Mingguo Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Luping Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Y.Z., P.Q., Y.J. and W. Zhang proposed the idea for the brain-inspired hierarchy. Y.Z. was in charge of the whole design. P.Q. proposed the ideas for the POG and the proof of its Turing completeness. Y.J. proposed the ideas for neuromorphic completeness, the EPG, the basic execution primitives and the constructive proof of its neuromorphic completeness. W. Zhang proposed the ideas for the ANA and the mapping from the EPG to it. P.Q. performed the experiment on the GPU. Y.J. performed the experiment on the FPSA. W. Zhang and G.W. performed the experiments on Tianjic. Y.J. and W. Zhang performed the experiments on the Boid model and QR decomposition for the revision. G.G. gave advice on the theory of architecture and hierarchy. L.S. was in charge of Tianjic work and proposed the idea to bridge dual-driven brain-inspired computing with artificial general intelligence. G.G., S.S., G.L., W.C. W. Zheng, F.C., J.P., R.Z., M.Z. and L.S. contributed to the analysis and interpretation of results. All authors contributed to the discussion of the design principle of the brain-inspired hierarchy. Y.Z., L.S., P.Q. and R.Z. revised the manuscript, with input from all authors. Y.Z. and L.S. supervised the project.

Corresponding authors

Correspondence to Youhui Zhang or Luping Shi.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Peer review information Nature thanks Oliver Rhodes and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Extended data figures and tables

Extended Data Fig. 1 POG.

a, Two sample operators: the left is a single mathematical operation and the right is a simple algorithm that consists of several computation operations. b, A sample operator graph for rectified linear units (ReLU). c, Parameter updater. More details are provided in Supplementary Information section 3.3.1. d, Main control-flow operators: conditional decider, conditional merger, true gate and false gate. e, Control-flow operator graphs of the branch and the loop. f, Synapse operator: it is enabled when any of the inputs arrive. i, input; o, output; T/F, true/false branch; P, parameter of the operator; P′, the new value of P; OGT/F, operator graph of the true/false branch; Body, operator graph of the loop body; Cond, operator graph of the loop condition.

Extended Data Fig. 2 Bicycle driving and tracking task.

a–e, POGs of the five neural network examples. Conv2d, two-dimensional convolution operator; MatMul, matrix multiplication operator; LIF, operator of the LIF model; Norm, normalization operator; W, b, weight and bias parameters for the corresponding operator. f, The overall relationships between these networks.

Extended Data Fig. 3 Resource consumption of the FPSA for different operators

.

Extended Data Fig. 4 The experiment using QR decomposition.

a, Pseudocode for QR decomposition by Givens rotation. b, The heuristic search algorithm on QR decomposition. Each step of this figure includes approximators that have been evaluated and the current priority queue. The number on each node represents the cost of that approximator. The red triangle represents the current strategy. Each step, the first tree in the queue is selected (green rectangle) and the leaves are replaced by the root approximator. The dashed circles represent the approximators that do not need to be constructed and evaluated. The whole procedure explores only four (out of 16) strategies. In this case, the final strategy happens to be the best, but in general, this algorithm is not guaranteed to produce the optimal result.

Extended Data Table 1 Universal approximators in the QR decomposition
Full size table
Extended Data Table 2 Granularity and cost of different strategies
Full size table
Extended Data Table 3 Part of the Tianjic primitives
Full size table
Extended Data Table 4 FPSA function blocks at 400 MHz, 45 nm
Full size table

Supplementary information

Supplementary Information

This file includes some mathematical proofs, a detailed introduction about each part of our hierarchy, detailed experiment description and analysis and an exhaustive discussion about the work. It also includes Supplementary Figures 1–11, Supplementary Tables 1-3, and additional references.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, Y., Qu, P., Ji, Y. et al. A system hierarchy for brain-inspired computing. Nature 586, 378–384 (2020). https://doi.org/10.1038/s41586-020-2782-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41586-020-2782-y

This article is cited by

Comments

By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing